Enterprise agent learns hidden business rules by observing actions
Continual Enterprise World Model Discovery in Dynamic Systems
Artificial Intelligence
Summary
In many companies, changing one piece of data can trigger other changes according to rules that are often unknown to outsiders. The authors study how a computer program can figure out these hidden rules by trying actions and watching what happens. This program keeps updating its understanding as the rules change over time. They tested this on a real enterprise system environment with many rules and showed their program learned and predicted outcomes better than previous methods.
What this means in practice
- •For enterprise software developers: Enable software agents to autonomously learn and adapt to hidden business rules within corporate applications without manual rule input.
- •For workflow automation teams: Improve automation reliability by building internal models of changing process rules to predict outcome effects before executing actions.
Authors
Shambhavi Mishra, David Vazquez, Perouz Taslakian, Marco Pedersoli, Jose Dolz, Issam H. Laradji
Abstract
In an enterprise system, updating one field can set another, create a record, or start an approval. These effects are produced by business rules that are not built into the platform but written by each organization and revised over time. An agent working in such a system cannot predict the result of its own actions without knowing these rules. We study continual enterprise world model discovery, where an agent starts without knowledge of these business rules and discovers them by interacting with records and observing the outcomes. From those observations it builds a world model, which it revises as the rules change. To evaluate this, we introduce EnterpriseWorldShift, built on a live ServiceNow environment with nine tables, 25 hidden rules and 600 evaluation actions. It presents four versions of the same enterprise world, with the tables and records held fixed while a rule is modified, then added, then removed, so that discovery, revision, extension and retirement are each tested in turn. Our Continual Discovery Agent (CDA) builds such a model and carries it from one world to the next. It predicts the effects of the hidden rules more accurately than looking them up for each question, the approach taken by prior work, by up to 8.98 IoU points, and it answers from its own model without querying the running system.